Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2031 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Diagram Understanding and Reasoning | DIAGRAMMA | 17 | Mar 16, 2026 | ||
| Retrosynthesis Prediction | ORDerly in-distribution (test) | 17 | Mar 16, 2026 | ||
| Reasoning | GSM8K | 17 | Apr 15, 2026 | ||
| Cross-view geo-localization | CVACT C-ALL (val) | 17 | Mar 16, 2026 | ||
| multi-hop reasoning | TriviaQA | 17 | Mar 24, 2026 | ||
| Hazard Detection and Temporal Localization | HomeSafe-Bench 1.0 (test) | 17 | Mar 13, 2026 | ||
| Novel View Synthesis | RealEstate10K 6 views (test) | 17 | Jun 4, 2026 | ||
| Natural Language Understanding | GLUE | 17 | Mar 13, 2026 | ||
| Text Embedding | MTEB v2 | 17 | Mar 13, 2026 | ||
| 10-class classification | FedCIFAR-10 Global Dir(0.5) (test) | 17 | Mar 13, 2026 | ||
| 10-class classification | FedCIFAR-10 Local Dir(0.5) (test) | 17 | Mar 13, 2026 | ||
| Autism Spectrum Disorder Classification | FedASD Global (test) | 17 | Mar 13, 2026 | ||
| Autism Spectrum Disorder Classification | FedASD Local (test) | 17 | Mar 13, 2026 | ||
| Skin lesion classification | FedSkin Global alpha=0.5 (test) | 17 | Mar 13, 2026 | ||
| Skin lesion classification | FedSkin alpha=0.5 (test) | 17 | Mar 13, 2026 | ||
| Skin lesion classification | FedSkin Global alpha=1 (test) | 17 | Mar 13, 2026 | ||
| Skin lesion classification | FedSkin Local alpha=1 (test) | 17 | Mar 13, 2026 | ||
| Image Editing | WeEdit Bilingual Benchmark 1.0 (test) | 17 | Mar 13, 2026 | ||
| Reasoning | Multilingual Benchmark | 17 | Mar 13, 2026 | ||
| Style | Multilingual Benchmark | 17 | Mar 13, 2026 | ||
| Translate | Multilingual Benchmark | 17 | Mar 13, 2026 | ||
| Rearrange | Multilingual Benchmark | 17 | Mar 13, 2026 | ||
| Delete | Multilingual Benchmark | 17 | Mar 13, 2026 | ||
| Replace | Multilingual Benchmark | 17 | Mar 13, 2026 | ||
| Add | Multilingual Benchmark | 17 | Mar 13, 2026 |